mannycalavera@feddit.uk to Technology@lemmy.worldEnglish · 2 days agoLinus Torvalds let Claude Code fix the Linux page cache. Then reviewers found a race.thenewstack.ioexternal-linkmessage-square162linkfedilinkarrow-up11arrow-down10file-text
arrow-up11arrow-down1external-linkLinus Torvalds let Claude Code fix the Linux page cache. Then reviewers found a race.thenewstack.iomannycalavera@feddit.uk to Technology@lemmy.worldEnglish · 2 days agomessage-square162linkfedilinkfile-text
minus-squareboonhet@sopuli.xyzlinkfedilinkEnglisharrow-up0·13 hours agoThe same happens when humans write code. Reviewers hopefully find some of their mistakes, then they fix them
minus-squareDarkCloud@lemmy.worldlinkfedilinkEnglisharrow-up0·13 hours agoTell me then, was the problem solved, the work done by the LLM? Was it considered good enough for a mainbranch? Or was it faulty/risky and require highly trained experts to catch? Then flagged, and only put into an experimental branch? How many ex-Oracle memory experts do you think are available for this work, in which even Linus didn’t catch the race condition? “Hey guys, nothing to see here if we have enough high level engineers fixing everything”.
minus-squarehirihit640@sh.itjust.workslinkfedilinkEnglisharrow-up0·11 hours ago Tell me then, was the problem solved, the work done by the LLM? partially Was it considered good enough for a mainbranch? Probably, if it took multiple experts to catch the bug. Or was it faulty/risky and require highly trained experts to catch? Then flagged, and only put into an experimental branch? As happens with human code all the time How many ex-Oracle memory experts do you think are available for this work, in which even Linus didn’t catch the race condition? No idea, at least one. A competent person like Linus can manage and direct competent code generation, whether that code is generated by an AI or an intern.
minus-squareDarkCloud@lemmy.worldlinkfedilinkEnglisharrow-up0·8 hours agoRight the guy who failed to catchy the problem in the generated code, will be fine.
The same happens when humans write code. Reviewers hopefully find some of their mistakes, then they fix them
Tell me then, was the problem solved, the work done by the LLM?
Was it considered good enough for a mainbranch?
Or was it faulty/risky and require highly trained experts to catch? Then flagged, and only put into an experimental branch?
How many ex-Oracle memory experts do you think are available for this work, in which even Linus didn’t catch the race condition?
“Hey guys, nothing to see here if we have enough high level engineers fixing everything”.
partially
Probably, if it took multiple experts to catch the bug.
As happens with human code all the time
No idea, at least one.
A competent person like Linus can manage and direct competent code generation, whether that code is generated by an AI or an intern.
Right the guy who failed to catchy the problem in the generated code, will be fine.